Data-Driven Prediction of Brain Stroke Risk Using Machine Learning Techniques on Healthcare

A brain stroke is a very serious health issue that is responsible for about 10% of death cases all over the world (nearly 6 million people) in 2019, and it is one of the top 10 causes of death and long-term disability in many countries. The medical community tries to turn this around by focusing on early diagnosis and treatment. Usually, other methods may not be available in developing regions where diagnosis and treatment are done using primitive tools. This project aims to employ the ever-increasing electronic health records together with data science to develop a predictive model that will detect high-risk individuals over stroke based on their health and lifestyle factors. The research is based on the Brain Stroke Dataset from Kaggle, which contains 4981 records with 11 attributes, including age, hypertension, heart disease, and smoking habits as the most important ones.